Merge tag 'riscv-for-linus-5.14-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux

Pull RISC-V fixes from Palmer Dabbelt:

- properly set the memory size, which fixes 32-bit systems

- allow initrd to load anywhere in memory, rather that restricting it
to the first 256MiB

- fix the 'mem=' parameter on 64-bit systems to properly account for
the maximum supported memory now that the kernel is outside the
linear map

- avoid installing mappings into the last 4KiB of memory, which
conflicts with error values

- avoid the stack from being freed while it is being walked

- a handful of fixes to the new copy to/from user routines

* tag 'riscv-for-linus-5.14-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux:
riscv: __asm_copy_to-from_user: Fix: Typos in comments
riscv: __asm_copy_to-from_user: Remove unnecessary size check
riscv: __asm_copy_to-from_user: Fix: fail on RV32
riscv: __asm_copy_to-from_user: Fix: overrun copy
riscv: stacktrace: pin the task's stack in get_wchan
riscv: Make sure the kernel mapping does not overlap with IS_ERR_VALUE
riscv: Make sure the linear mapping does not use the kernel mapping
riscv: Fix memory_limit for 64-bit kernel
RISC-V: load initrd wherever it fits into memory
riscv: Fix 32-bit RISC-V boot failure

arch/riscv/include/asm/efi.h

···
 
 #define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE)
 
-/* Load initrd at enough distance from DRAM start */
+/* Load initrd anywhere in system RAM */
 static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr)
 {
-	return image_addr + SZ_256M;
+	return ULONG_MAX;
 }
 
 #define alloc_screen_info(x...)		(&screen_info)

arch/riscv/kernel/stacktrace.c

···
 {
 	unsigned long pc = 0;
 
-	if (likely(task && task != current && !task_is_running(task)))
+	if (likely(task && task != current && !task_is_running(task))) {
+		if (!try_get_task_stack(task))
+			return 0;
 		walk_stackframe(task, NULL, save_wchan, &pc);
+		put_task_stack(task);
+	}
 	return pc;
 }
 

arch/riscv/lib/uaccess.S

···
 	 * t0 - end of uncopied dst
 	 */
 	add	t0, a0, a2
-	bgtu	a0, t0, 5f
 
 	/*
 	 * Use byte copy only if too small.
+	 * SZREG holds 4 for RV32 and 8 for RV64
 	 */
-	li	a3, 8*SZREG /* size must be larger than size in word_copy */
+	li	a3, 9*SZREG /* size must be larger than size in word_copy */
 	bltu	a2, a3, .Lbyte_copy_tail
 
 	/*
-	 * Copy first bytes until dst is align to word boundary.
+	 * Copy first bytes until dst is aligned to word boundary.
 	 * a0 - start of dst
 	 * t1 - start of aligned dst
 	 */
 	addi	t1, a0, SZREG-1
 	andi	t1, t1, ~(SZREG-1)
 	/* dst is already aligned, skip */
-	beq	a0, t1, .Lskip_first_bytes
+	beq	a0, t1, .Lskip_align_dst
 1:
 	/* a5 - one byte for copying data */
 	fixup lb      a5, 0(a1), 10f
···
 	addi	a0, a0, 1	/* dst */
 	bltu	a0, t1, 1b	/* t1 - start of aligned dst */
 
-.Lskip_first_bytes:
+.Lskip_align_dst:
 	/*
 	 * Now dst is aligned.
 	 * Use shift-copy if src is misaligned.
···
 	 *
 	 * a0 - start of aligned dst
 	 * a1 - start of aligned src
-	 * a3 - a1 & mask:(SZREG-1)
 	 * t0 - end of aligned dst
 	 */
-	addi	t0, t0, -(8*SZREG-1) /* not to over run */
+	addi	t0, t0, -(8*SZREG) /* not to over run */
 2:
 	fixup REG_L   a4,        0(a1), 10f
 	fixup REG_L   a5,    SZREG(a1), 10f
···
 	addi	a1, a1, 8*SZREG
 	bltu	a0, t0, 2b
 
-	addi	t0, t0, 8*SZREG-1 /* revert to original value */
+	addi	t0, t0, 8*SZREG /* revert to original value */
 	j	.Lbyte_copy_tail
 
 .Lshift_copy:
···
 	 * For misaligned copy we still perform aligned word copy, but
 	 * we need to use the value fetched from the previous iteration and
 	 * do some shifts.
-	 * This is safe because reading less than a word size.
+	 * This is safe because reading is less than a word size.
 	 *
 	 * a0 - start of aligned dst
 	 * a1 - start of src
···
 	 */
 	/* calculating aligned word boundary for dst */
 	andi	t1, t0, ~(SZREG-1)
-	/* Converting unaligned src to aligned arc */
+	/* Converting unaligned src to aligned src */
 	andi	a1, a1, ~(SZREG-1)
 
 	/*
···
 	 * t3 - prev shift
 	 * t4 - current shift
 	 */
-	slli	t3, a3, LGREG
+	slli	t3, a3, 3 /* converting bytes in a3 to bits */
 	li	a5, SZREG*8
 	sub	t4, a5, t3
 
-	/* Load the first word to combine with seceond word */
+	/* Load the first word to combine with second word */
 	fixup REG_L   a5, 0(a1), 10f
 
 3:
···
 	 * a1 - start of remaining src
 	 * t0 - end of remaining dst
 	 */
-	bgeu	a0, t0, 5f
+	bgeu	a0, t0, .Lout_copy_user  /* check if end of copy */
 4:
 	fixup lb      a5, 0(a1), 10f
 	addi	a1, a1, 1	/* src */
···
 	addi	a0, a0, 1	/* dst */
 	bltu	a0, t0, 4b	/* t0 - end of dst */
 
-5:
+.Lout_copy_user:
 	/* Disable access to user memory */
 	csrc CSR_STATUS, t6
 	li	a0, 0

arch/riscv/mm/init.c

···
 }
 
 /*
- * The default maximal physical memory size is -PAGE_OFFSET,
- * limit the memory size via mem.
+ * The default maximal physical memory size is -PAGE_OFFSET for 32-bit kernel,
+ * whereas for 64-bit kernel, the end of the virtual address space is occupied
+ * by the modules/BPF/kernel mappings which reduces the available size of the
+ * linear mapping.
+ * Limit the memory size via mem.
  */
+#ifdef CONFIG_64BIT
+static phys_addr_t memory_limit = -PAGE_OFFSET - SZ_4G;
+#else
 static phys_addr_t memory_limit = -PAGE_OFFSET;
+#endif
 
 static int __init early_mem(char *p)
 {
···
 {
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
-	phys_addr_t max_mapped_addr = __pa(~(ulong)0);
+	phys_addr_t __maybe_unused max_mapped_addr;
 	phys_addr_t dram_end;
 
 #ifdef CONFIG_XIP_KERNEL
···
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
 	dram_end = memblock_end_of_DRAM();
+
+#ifndef CONFIG_64BIT
 	/*
 	 * memblock allocator is not aware of the fact that last 4K bytes of
 	 * the addressable memory can not be mapped because of IS_ERR_VALUE
 	 * macro. Make sure that last 4k bytes are not usable by memblock
-	 * if end of dram is equal to maximum addressable memory.
+	 * if end of dram is equal to maximum addressable memory.  For 64-bit
+	 * kernel, this problem can't happen here as the end of the virtual
+	 * address space is occupied by the kernel mapping then this check must
+	 * be done in create_kernel_page_table.
 	 */
+	max_mapped_addr = __pa(~(ulong)0);
 	if (max_mapped_addr == (dram_end - 1))
 		memblock_set_current_limit(max_mapped_addr - 4096);
+#endif
 
 	min_low_pfn = PFN_UP(memblock_start_of_DRAM());
 	max_low_pfn = max_pfn = PFN_DOWN(dram_end);
···
 	BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
 	BUG_ON((kernel_map.phys_addr % map_size) != 0);
 
+#ifdef CONFIG_64BIT
+	/*
+	 * The last 4K bytes of the addressable memory can not be mapped because
+	 * of IS_ERR_VALUE macro.
+	 */
+	BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
+#endif
+
 	pt_ops.alloc_pte = alloc_pte_early;
 	pt_ops.get_pte_virt = get_pte_virt_early;
 #ifndef __PAGETABLE_PMD_FOLDED
···
 		if (start <= __pa(PAGE_OFFSET) &&
 		    __pa(PAGE_OFFSET) < end)
 			start = __pa(PAGE_OFFSET);
+		if (end >= __pa(PAGE_OFFSET) + memory_limit)
+			end = __pa(PAGE_OFFSET) + memory_limit;
 
 		map_size = best_map_size(start, end - start);
 		for (pa = start; pa < end; pa += map_size) {